English
Related papers

Related papers: Structural Rationale Distillation via Reasoning Sp…

200 papers

Reasoning with large language models often benefits from generating multiple chains-of-thought, but existing aggregation strategies are typically trajectory-level (e.g., selecting the best trace or voting on the final answer), discarding…

Computation and Language · Computer Science 2026-02-27 Roy Miles , Aysim Toker , Andreea-Maria Oncescu , Songcen Xu , Jiankang Deng , Ismail Elezi

Small Language Models (SLMs) are attractive for cost-sensitive and resource-limited settings due to their efficient, low-latency inference. However, they often struggle with complex, knowledge-intensive tasks that require structured…

Artificial Intelligence · Computer Science 2026-02-03 Shaoxiong Yang , Junting Li , Mengyuan Zhang , Chao Li , Wei Liu , Jian Luan

Large language models have led to significant progress across many NLP tasks, although their massive sizes often incur substantial computational costs. Distillation has become a common practice to compress these large and highly capable…

Computation and Language · Computer Science 2026-01-06 Zishun Yu , Shangzhe Li , Xinhua Zhang

We introduce a novel approach to large language model (LLM) distillation by formulating it as a constrained reinforcement learning problem. While recent work has begun exploring the integration of task-specific rewards into distillation…

Machine Learning · Computer Science 2025-09-30 Matthieu Zimmer , Xiaotong Ji , Tu Nguyen , Haitham Bou Ammar

Query-service relevance prediction in e-commerce search systems faces strict latency requirements that prevent the direct application of Large Language Models (LLMs). To bridge this gap, we propose a two-stage reasoning distillation…

Information Retrieval · Computer Science 2026-01-27 Runze Xia , Yupeng Ji , Yuxi Zhou , Haodong Liu , Teng Zhang , Piji Li

Distilling the thinking traces of a Large Language Model (LLM) with reasoning capabilities into a smaller model has been proven effective. Yet, there is a scarcity of work done on how model performances scale with the quantity of…

Computation and Language · Computer Science 2025-10-08 Muyu He , Muhammad Ali Shafique , Anand Kumar , Tsach Mackey , Nazneen Rajani

Knowledge Distillation (KD) emerges as one of the most promising compression technologies to run advanced deep neural networks on resource-limited devices. In order to train a small network (student) under the guidance of a large network…

Machine Learning · Computer Science 2023-12-15 Yi Guo , Yiqian He , Xiaoyang Li , Haotong Qin , Van Tung Pham , Yang Zhang , Shouda Liu

Adapting large language models (LLMs) to long-context tasks requires post-training methods that remain accurate and coherent over thousands of tokens. Existing approaches are limited in several ways: 1) off-policy methods such as supervised…

Computation and Language · Computer Science 2026-05-13 Miguel Moura Ramos , Duarte M. Alves , André F. T. Martins

Self-Consistency mitigates hallucinations in Large Language Models (LLMs) by sampling multiple reasoning paths,but it lacks a systematic approach to determine the optimal number of samples or select the most faithful rationale. To address…

Computation and Language · Computer Science 2025-02-05 Guangya Wan , Yuqi Wu , Jie Chen , Sheng Li

Inference-time scaling enhances the reasoning ability of a language model (LM) by extending its chain-of-thought (CoT). However, existing approaches typically generate the entire reasoning chain in a single forward pass, which often leads…

Computation and Language · Computer Science 2025-10-20 Siheng Xiong , Ali Payani , Faramarz Fekri

Distilling multi-step reasoning abilities from large language models (LLMs) into compact student models remains challenging due to noisy rationales, hallucinated supervision, and static teacher-student interactions. Existing reasoning…

Computation and Language · Computer Science 2026-05-14 Kasidit Sermsri , Teerapong Panboonyuen

Recent advancements in large language models (LLMs) have demonstrated remarkable reasoning capabilities through long chain-of-thought (CoT) reasoning. The R1 distillation scheme has emerged as a promising approach for training…

Artificial Intelligence · Computer Science 2025-03-21 Yijia Luo , Yulin Song , Xingyao Zhang , Jiaheng Liu , Weixun Wang , GengRu Chen , Wenbo Su , Bo Zheng

Chain-of-thought prompting (e.g., "Let's think step-by-step") primes large language models to verbalize rationalization for their predictions. While chain-of-thought can lead to dramatic performance gains, benefits appear to emerge only for…

Computation and Language · Computer Science 2024-04-17 Liunian Harold Li , Jack Hessel , Youngjae Yu , Xiang Ren , Kai-Wei Chang , Yejin Choi

Knowledge distillation is the procedure of transferring "knowledge" from a large model (the teacher) to a more compact one (the student), often being used in the context of model compression. When both models have the same architecture,…

Machine Learning · Computer Science 2022-06-20 Minh Pham , Minsu Cho , Ameya Joshi , Chinmay Hegde

Recent advances in large language models (LLMs) have led to the development of thinking language models that generate extensive internal reasoning chains before producing responses. While these models achieve improved performance,…

Machine Learning · Computer Science 2025-10-23 Constantin Venhoff , Iván Arcuschin , Philip Torr , Arthur Conmy , Neel Nanda

Although large language models (LLMs) have recently achieved remarkable performance on various complex reasoning benchmarks, the academic community still lacks an in-depth understanding of base model training processes and data quality. To…

Computation and Language · Computer Science 2025-05-14 Xiaoyu Tian , Sitong Zhao , Haotian Wang , Shuaiting Chen , Yiping Peng , Yunjie Ji , Han Zhao , Xiangang Li

The detection of mental health problems from social media and the interpretation of these results have been extensively explored. Research has shown that incorporating clinical symptom information into a model enhances domain expertise,…

Computation and Language · Computer Science 2025-10-28 Hoyun Song , Huije Lee , Jisu Shin , Sukmin Cho , Changgeon Ko , Jong C. Park

Recent advancements in large language models (LLMs) have demonstrated remarkable reasoning capabilities. However, single-shot inference often yields unreliable results for complex reasoning tasks, leading researchers to explore multiple…

Machine Learning · Computer Science 2025-02-14 Zhi Zhou , Tan Yuhao , Zenan Li , Yuan Yao , Lan-Zhe Guo , Xiaoxing Ma , Yu-Feng Li

Large language models (LLMs) excel at complex reasoning tasks but remain computationally expensive, limiting their practical deployment. To address this, recent works have focused on distilling reasoning capabilities into smaller language…

Computation and Language · Computer Science 2025-11-06 Minki Kang , Jongwon Jeong , Seanie Lee , Jaewoong Cho , Sung Ju Hwang

Context distillation compresses contextual information into model parameters, yet existing methods often ignore how multiple distilled latent memories should be stored, retrieved, and safely activated in non-oracle settings. We formulate…

Machine Learning · Computer Science 2026-05-29 Ziyang Zheng , Zeju Li , Xiangyu Wen , Jianyuan Zhong , Junhua Huang , Lei Chen , Mingxuan Yuan , Qiang Xu